Deep Tracking by Tagging


Short name:

DpTrack_16

Benchmark:

Description:

Public DPM detections are used and the tracking is achieved by assigning each person a different tag on an 8 frame video clips. By sliding 4 frame at a time and using the overlapping information tracking is achieved through out the video.

Hardware:

3.0GHz,1_Core_and_Titan_X_Pascal

Detector:

Public

Processing:

Batch

Last submitted:

September 03, 2019 (1 month ago)

Published:

July 12, 2019 at 22:21:19 CET

Submissions:

4

Open source:

No

Project page / code:

n/a

Reference:

Anonymous submission

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
59.379.41.427.4 % 24.6 % 8,56663,6032,0451,5553.0GHz,1_Core_and_Titan_X_PascalPublic
IDF1ID PrecisionID Recall
52.864.244.8

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0155.647.978.41.32343.5 % 13.0 % 5812,2164050
MOT16-0369.259.279.53.114845.3 % 10.1 % 4,62127,299249486
MOT16-0656.250.381.10.522133.9 % 24.9 % 6383,991424167
MOT16-0756.446.979.31.05424.1 % 7.4 % 4806,529115136
MOT16-0834.736.581.01.06314.3 % 33.3 % 60310,23893122
MOT16-1247.055.079.80.48622.1 % 44.2 % 3494,0044141
MOT16-1436.733.676.41.71649.1 % 31.1 % 1,2949,3261,083553

Raw data:

n/a


DpTrack_16